Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    semicolon and parentheses in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code delimiters and separators

    np_acts-logits-general · gemini-2.0-flash

    closing code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.59
     OFDb
    -0.52
    xtext
    -0.52
    绪
    -0.48
    ↵↵
    -0.45
    Vidite
    -0.45
     Peter
    -0.44
     ostavi
    -0.44
     voie
    -0.43
     Paglinawan
    -0.43
    POSITIVE LOGITS
    AutoresizingMask
    0.79
    enumi
    0.74
    UserScript
    0.73
     Efq
    0.70
    endphp
    0.70
    存于互联网档案馆
    0.70
    σθαι
    0.69
    VersionUID
    0.68
     habet
    0.67
    cipar
    0.65
    Act Density 0.071%

    No Known Activations